---
title: esm2_t48_15B_UR50D
description: ESM-2 is a state-of-the-art protein model trained on a masked language modelling objective. It is suitable for fine-tuning on a wide range of tasks that take protein sequences as input. For detailed information on the model architecture and training data, please refer to the accompanying paper. You may also be interested in some demo notebooks (PyTorch, TensorFlow) which demonstrate how to…
tags:
- esm
- fill-mask
- protein
- sequence
license: mit
source_url: https://huggingface.co/facebook/esm2_t48_15B_UR50D
---

# esm2_t48_15B_UR50D

> **Mirrored metadata.** This card is reproduced on Atlas for discovery. The artifact itself is not hosted here — follow the source link for the files, and refer to the upstream licence for terms of use.

ESM-2 is a state-of-the-art protein model trained on a masked language modelling objective. It is suitable for fine-tuning on a wide range of tasks that take protein sequences as input. For detailed information on the model architecture and training data, please refer to the accompanying paper. You may also be interested in some demo notebooks (PyTorch, TensorFlow) which demonstrate how to…

Upstream identifier: `facebook/esm2_t48_15B_UR50D`.

**Source:** https://huggingface.co/facebook/esm2_t48_15B_UR50D

**Licence:** mit

_This model is part of the Atlas demo catalogue. See the repository history for provenance._